This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
-
-
Notifications
You must be signed in to change notification settings - Fork 37
/
regression.pyi
155 lines (140 loc) · 5.11 KB
/
regression.pyi
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http:https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
from typing import overload
from typing import Iterable, Optional, Tuple, TypeVar
from pyspark.rdd import RDD
from pyspark.mllib._typing import VectorLike
from pyspark.context import SparkContext
from pyspark.mllib.linalg import Vector
from pyspark.mllib.util import Saveable, Loader
from pyspark.streaming.dstream import DStream
from numpy import ndarray # type: ignore[import]
K = TypeVar("K")
class LabeledPoint:
label: int
features: Vector
def __init__(self, label: float, features: Iterable[float]) -> None: ...
def __reduce__(self) -> Tuple[type, Tuple[bytes]]: ...
class LinearModel:
def __init__(self, weights: Vector, intercept: float) -> None: ...
@property
def weights(self) -> Vector: ...
@property
def intercept(self) -> float: ...
class LinearRegressionModelBase(LinearModel):
@overload
def predict(self, x: Vector) -> float: ...
@overload
def predict(self, x: RDD[Vector]) -> RDD[float]: ...
class LinearRegressionModel(LinearRegressionModelBase):
def save(self, sc: SparkContext, path: str) -> None: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> LinearRegressionModel: ...
class LinearRegressionWithSGD:
@classmethod
def train(
cls,
data: RDD[LabeledPoint],
iterations: int = ...,
step: float = ...,
miniBatchFraction: float = ...,
initialWeights: Optional[VectorLike] = ...,
regParam: float = ...,
regType: Optional[str] = ...,
intercept: bool = ...,
validateData: bool = ...,
convergenceTol: float = ...,
) -> LinearRegressionModel: ...
class LassoModel(LinearRegressionModelBase):
def save(self, sc: SparkContext, path: str) -> None: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> LassoModel: ...
class LassoWithSGD:
@classmethod
def train(
cls,
data: RDD[LabeledPoint],
iterations: int = ...,
step: float = ...,
regParam: float = ...,
miniBatchFraction: float = ...,
initialWeights: Optional[VectorLike] = ...,
intercept: bool = ...,
validateData: bool = ...,
convergenceTol: float = ...,
) -> LassoModel: ...
class RidgeRegressionModel(LinearRegressionModelBase):
def save(self, sc: SparkContext, path: str) -> None: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> RidgeRegressionModel: ...
class RidgeRegressionWithSGD:
@classmethod
def train(
cls,
data: RDD[LabeledPoint],
iterations: int = ...,
step: float = ...,
regParam: float = ...,
miniBatchFraction: float = ...,
initialWeights: Optional[VectorLike] = ...,
intercept: bool = ...,
validateData: bool = ...,
convergenceTol: float = ...,
) -> RidgeRegressionModel: ...
class IsotonicRegressionModel(Saveable, Loader[IsotonicRegressionModel]):
boundaries: ndarray
predictions: ndarray
isotonic: bool
def __init__(
self, boundaries: ndarray, predictions: ndarray, isotonic: bool
) -> None: ...
@overload
def predict(self, x: Vector) -> ndarray: ...
@overload
def predict(self, x: RDD[Vector]) -> RDD[ndarray]: ...
def save(self, sc: SparkContext, path: str) -> None: ...
@classmethod
def load(cls, sc: SparkContext, path: str) -> IsotonicRegressionModel: ...
class IsotonicRegression:
@classmethod
def train(
cls, data: RDD[VectorLike], isotonic: bool = ...
) -> IsotonicRegressionModel: ...
class StreamingLinearAlgorithm:
def __init__(self, model: LinearModel) -> None: ...
def latestModel(self) -> LinearModel: ...
def predictOn(self, dstream: DStream[VectorLike]) -> DStream[float]: ...
def predictOnValues(
self, dstream: DStream[Tuple[K, VectorLike]]
) -> DStream[Tuple[K, float]]: ...
class StreamingLinearRegressionWithSGD(StreamingLinearAlgorithm):
stepSize: float
numIterations: int
miniBatchFraction: float
convergenceTol: float
def __init__(
self,
stepSize: float = ...,
numIterations: int = ...,
miniBatchFraction: float = ...,
convergenceTol: float = ...,
) -> None: ...
def setInitialWeights(
self, initialWeights: VectorLike
) -> StreamingLinearRegressionWithSGD: ...
def trainOn(self, dstream: DStream[LabeledPoint]) -> None: ...